IDENTIFIKASI JENIS KOPI MENGGUNAKAN SENSOR E-NOSE DENGAN METODE PEMBELAJARAN JARINGAN SYARAF TIRUAN BACKPROPAGATION

Dwi Dian Novita; Akhmad Bangsawan Sesunan; Mareli Telaumbanua; Sugeng Triyono; Tri Wahyu Saputra

doi:10.29303/jrpb.v9i2.241

IDENTIFIKASI JENIS KOPI MENGGUNAKAN SENSOR E-NOSE DENGAN METODE PEMBELAJARAN JARINGAN SYARAF TIRUAN BACKPROPAGATION

Jurnal Ilmiah Rekayasa Pertanian dan Biosistem ◽

10.29303/jrpb.v9i2.241 ◽

2021 ◽

Vol 9 (2) ◽

pp. 205-217

Author(s):

Dwi Dian Novita ◽

Akhmad Bangsawan Sesunan ◽

Mareli Telaumbanua ◽

Sugeng Triyono ◽

Tri Wahyu Saputra

Keyword(s):

Electronic Nose ◽

Hidden Layer

Electronic Nose merupakan sebuah alat yang dapat menirukan cara kerja hidung manusia. Kopi memiliki beberapa jenis antara lain kopi robusta, kopi arabika dan kopi luwak. Setiap jenis kopi memiliki aroma khas tersendiri sehingga dibutuhkan suatu alat untuk dapat membedakannya secara cepat dan tepat. Penelitian ini bertujuan untuk mengidentifikasi jenis – jenis kopi berdasarkan perbedaan aroma yang terdapat didalamnya. Penelitian ini menggunakan biji kopi natural robusta Lampung (kopi 1), robusta natural (kopi 2), robusta semiwash (kopi 3), natural arabika (kopi 4), arabika fullwash (kopi 5). Penelitian menggunakan metode JST backpropagation dengan arsitektur jaringan 1 input, 2 hidden layer, dan 1 Output. Fungsi aktivasi terbaik pada pelatihan model JST adalah logsig-logsig-tansig dengan nilai RMSE sebesar 0,003602368 dan R2 sebesar 0,991. Hasil klasifikasi jenis kopi menggunakan sensor E-Nose dengan metode JST Backpropagation menunjukkan persentase keberhasilan identifikasi 5 jenis kopi, yaitu: kopi natural robusta lampung yaitu 100%, kopi natural robusta 100%, kopi robusta semiwash 72%, kopi arabika natural 100%, dan kopi arabika fullwash 100%.

Download Full-text

An Electronic Nose Technology to Quantify Pyrethroid Pesticide Contamination in Tea

Chemosensors ◽

10.3390/chemosensors8020030 ◽

2020 ◽

Vol 8 (2) ◽

pp. 30

Author(s):

Xiaoyan Tang ◽

Wenmin Xiao ◽

Tao Shang ◽

Shanyan Zhang ◽

Xiaoyang Han ◽

...

Keyword(s):

Neural Network ◽

Electronic Nose ◽

Bp Neural Network ◽

Back Propagation ◽

Detection Methods ◽

Layer Model ◽

Pyrethroid Pesticide ◽

Pyrethroid Pesticides ◽

Hidden Layer ◽

Network Pattern

The contamination of tea with toxic pesticides is a major concern. Additionally, because of improved detection methods, importers are increasingly rejecting contaminated teas. Here, we describe an electronic nose technique for the rapid detection of pyrethroid pesticides (cyhalothrin, bifenthrin, and fenpropathrin) in tea. Using a PEN 3 electronic nose, the text screened a group of metal oxide sensors and determined that four of them (W5S, W1S, W1W, and W2W) are suitable for the detection of the same pyrethroid pesticide in different concentrations and five of them (W5S, W1S, W1W, W2W, and W2S) are suitable for the detection of pyrethroid pesticide. The models for the determination of cyhalothrin, bifenthrin, and fenpropathrin are established by PLS method. Next, using back propagation (BP) neural network technology, we developed a three-hidden-layer model and a two-hidden-layer model to differentiate among the three pesticides. The accuracy of the three models is 96%, 92%, and 88%, respectively. The recognition accuracies of the three-hidden-layer BP neural network pattern and two-hidden-layer BP neural network pattern are 98.75% and 97.08%, respectively. Our electronic nose system accurately detected and quantified pyrethroid pesticides in tea leaves. We propose that this tool is now ready for practical application in the tea industry.

Download Full-text

DETEKSI KUALITAS TEMBAKAU BERDASARKAN AROMA BERBASIS ELECTRONIC NOSE

E-Link : Jurnal Teknik Elektro dan Informatika ◽

10.30587/e-link.v16i1.2096 ◽

2021 ◽

Vol 16 (1) ◽

pp. 37

Author(s):

Misbah Misbah ◽

Nurul Arif ◽

Yoedo Ageng Suryo

Keyword(s):

Neural Network ◽

Electronic Nose ◽

Output Layer ◽

Input Layer ◽

Hidden Layer

Tembakau mempunyai aroma khas, yang dihasilkan dari bahan organik yang mudah menguap dan yang tidakmudah menguap. Kualitas tembakau ditentukan dari proses fermentasi dan pengeringan. Pada industri rokok,penentuan kualitas tembakau dilakukan oleh tenaga ahli dengan mengandalkan indra penciuman. Hal iniberpotensi menghasilkan tingkat kesalahan yang tinggi. Electronic nose dapat dijadikan salah satu solusidalam menentukan kualitas tembakau. Electronic nose terdiri dari beberapa sensor gas dan unit pengolah data. Sensor gas yang dipakai adalah MQ4, MQ7, MQ 135 dan MQ137. Sedangkan pada unit pengolah dataterdapat algoritma kecerdasan buatan menggunakan neural network. Neural network terdiri dari 4 neuron pada input layer, 25 neuron pada hidden layer dan 2 neuron pada output layer dengan fungsi aktivasi TanSig. Dari hasil pengujian sistem ini dapat mengidentifikasi tembakau yang baik, sedang dan jelek dengan tingkatkeakurasiaan 95%.

Download Full-text

Detection of Escherichia coli in Packaged Alfalfa Sprouts with an Electronic Nose and an Artificial Neural Network

Journal of Food Protection ◽

10.4315/0362-028x-69.8.1844 ◽

2006 ◽

Vol 69 (8) ◽

pp. 1844-1850 ◽

Cited By ~ 16

Author(s):

UBONRAT SIRIPATRAWAN ◽

JOHN E. LINZ ◽

BRUCE R. HARTE

Keyword(s):

Neural Network ◽

Escherichia Coli ◽

Artificial Neural Network ◽

Transfer Function ◽

Electronic Nose ◽

E Coli ◽

Output Layer ◽

Artificial Neural ◽

Alfalfa Sprouts ◽

Hidden Layer

A rapid method for the detection of Escherichia coli (ATCC 25922) in packaged alfalfa sprouts was developed. Volatile compounds from the headspace of packaged alfalfa sprouts, inoculated with E. coli and incubated at 10°C for 1, 2, and 3 days, were collected and analyzed. Uninoculated sprouts were used as control samples. An electronic nose with 12 metal oxide electronic sensors was used to monitor changes in the composition of the gas phase of the package headspace with respect to volatile metabolites produced by E. coli. The electronic nose was able to differentiate between samples with and without E. coli. To predict the number of E. coli in packaged alfalfa sprouts, an artificial neural network was used, which included an input layer, a hidden layer, and an output layer, with a hyperbolic tangent sigmoidal transfer function in the hidden layer and a linear transfer function in the output layer. The network was shown to be capable of correlating voltametric responses with the number of E. coli. A good prediction was possible, as measured by a regression coefficient (R2 = 0.903) between the actual and predicted data. In conjunction with the artificial neural network, the electronic nose proved to have the ability to detect E. coli in packaged alfalfa sprouts.

Download Full-text